Rewrite component

A component that rewrites a user query.

---

A Rewrite component uses a specified LLM to rewrite a user query from the Interact component, based on the context of previous dialogues.

Scenarios

A Rewrite component is essential when you need to optimize a user query based on the context of previous conversations. It is usually the upstream component of a Retrieval component.

NOTE

See also the Keyword component, a similar component used for multi-turn optimization.

Configurations

NOTE

The Rewrite component uses the user-agent interaction from the Interact component as its data input. Therefore, there is no need to specify its data inputs in the Configurations.

Model

Click the dropdown menu of Model to show the model configuration window.

• Model: The chat model to use.
  • Ensure you set the chat model correctly on the Model providers page.
  • You can use different models for different components to increase flexibility or improve overall performance.
• Freedom: A shortcut to Temperature, Top P, Presence penalty, and Frequency penalty settings, indicating the freedom level of the model.
  This parameter has three options:
  • Improvise: Produces more creative responses.
  • Precise: (Default) Produces more conservative responses.
  • Balance: A middle ground between Improvise and Precise.
• Temperature: The randomness level of the model's output.
  Defaults to 0.1.
  • Lower values lead to more deterministic and predictable outputs.
  • Higher values lead to more creative and varied outputs.
  • A temperature of zero results in the same output for the same prompt.
• Top P: Nucleus sampling.
  • Reduces the likelihood of generating repetitive or unnatural text by setting a threshold P and restricting the sampling to tokens with a cumulative probability exceeding P.
  • Defaults to 0.3.
• Presence penalty: Encourages the model to include a more diverse range of tokens in the response.
  • A higher presence penalty value results in the model being more likely to generate tokens not yet been included in the generated text.
  • Defaults to 0.4.
• Frequency penalty: Discourages the model from repeating the same words or phrases too frequently in the generated text.
  • A higher frequency penalty value results in the model being more conservative in its use of repeated tokens.
  • Defaults to 0.7.
• Max tokens: Sets the maximum length of the model's output, measured in the number of tokens.
  • Defaults to 512.
  • If disabled, you lift the maximum token limit, allowing the model to determine the number of tokens in its responses.

NOTE

• It is not necessary to stick with the same model for all components. If a specific model is not performing well for a particular task, consider using a different one.
• If you are uncertain about the mechanism behind Temperature, Top P, Presence penalty, and Frequency penalty, you can simply choose one of the three options of Freedom.

Message window size

An integer specifying the number of previous dialogue rounds to input into the LLM. For example, if it is set to 12, the tokens from the last 12 dialogue rounds will be fed to the LLM. This feature consumes additional tokens.

Defaults to 1.

IMPORTANT

This feature is used for multi-turn dialogue only. If your Categorize component is not part of a multi-turn dialogue (i.e., it is not in a loop), leave this field as-is.

Examples

Explore our customer service agent template, where the Rewrite component (component ID: Refine Question) is used to optimize a product-specific user query based on context of previous dialogues before passing it on to the Retrieval component.

1. Click the Agent tab at the top center of the page to access the Agent page.
2. Click + Create agent on the top right of the page to open the agent template page.
3. On the agent template page, hover over the Customer service card and click Use this template.
4. Name your new agent and click OK to enter the workflow editor.
5. Click on the Rewrite component to display its Configuration window.